Post-Cutoff
Search For AI agents

NVIDIANemotron 3 familyCurrentReasoning modelReleased 11 Mar 2026

NVIDIA Nemotron 3 Super (120B-A12B)

Mid-size open reasoning model, widely hosted (Bedrock, NIM, OpenRouter).

Model idnvidia/nemotron-3-super-120b-a12b

Price$0.08 in, $0.45 out per 1M tokens

Checked29 September 2026

Knows up to June 2025

2,016events after its cutoff

89 historic, 466 major. 501 days of news.

It launched on 11 March 2026, already missing 107 of them. Coverage before 2026 is thin (80 entries for 2025), so this count is a floor.

Five things it has never heard of

Its cutoff, June 2025, is before this chart starts: every mark here is news it has never seen.

How to call it

4 ways to use NVIDIA Nemotron 3 Super (120B-A12B), with the model id each provider expects.

Providers, model ids, endpoints and docs for NVIDIA Nemotron 3 Super (120B-A12B)
ProviderModel idEndpointDocs
NVIDIA API (build.nvidia.com) nvidia/nemotron-3-super-120b-a12b https://integrate.api.nvidia.com/v1/chat/completions build.nvidia.com
AWS Bedrock nvidia.nemotron-super-3-120b docs.aws.amazon.com
OpenRouter nvidia/nemotron-3-super-120b-a12b openrouter.ai
Hugging Face huggingface.co

Pricing

Prices for NVIDIA Nemotron 3 Super (120B-A12B)
Input$0.08 per 1M tokens
Output$0.45 per 1M tokens

As published: “per 1M tokens (USD) on OpenRouter; NVIDIA hosted pricing not verified”.

Source: openrouter.ai, checked 29 September 2026.

Specs

Input
Text
Output
Text
Context window
1,000,000 tokens
Max output
Not published
Open weights
Yes
Licence
NVIDIA Open Model License
Training cutoff
June 2025
Released
11 March 2026
Status
Current
Type
Reasoning model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Efficient hybrid LatentMoE for agents

    120B total / 12B active hybrid Mamba-2 + MoE + attention, built for high-volume agentic workloads with up to 1M context (256K default).

    Source: huggingface.co

  • Managed on AWS Bedrock

    Found after launch

    One of the few NVIDIA open models offered as a serverless Bedrock model (nvidia.nemotron-super-3-120b).

    Source: docs.aws.amazon.com

Four assistants, one scale

NVIDIA Nemotron 3 Super (120B-A12B) is added as a fifth row. Each row runs from what the model knows (graphite) through the months between its cutoff and its launch (hatched) to today (pink).

  1. GPT-6 Astra 271 at launch, 1,863 today
  2. Claude Opus 5.5 372 at launch, 1,795 today
  3. Gemini 4 Hydrogen 1,863 at launch, 1,889 today
  4. Grok 4.7 387 at launch, 1,829 today
  5. NVIDIA Nemotron 3 Super (120B-A12B) 107 at launch, 2,016 today
Show as a table
ModelCutoffReleasedMissing at launchMissing today
GPT-6 AstraApril 20263 September 20262711,863
Claude Opus 5.5June 202622 September 20263721,795
Gemini 4 HydrogenMarch 202612 November 20261,8631,889
Grok 4.7May 202621 September 20263871,829
NVIDIA Nemotron 3 Super (120B-A12B)June 202511 March 20261072,016

Notes

Knowledge cutoff = pre-training (Jun 2025); post-training to Feb 2026. Also FP8/NVFP4 repos. Free tier on OpenRouter (:free).

curl https://integrate.api.nvidia.com/v1/chat/completions -H "Authorization: Bearer $NVIDIA_API_KEY" -H "Content-Type: application/json" \
 -d '{"model":"nvidia/nemotron-3-super-120b-a12b","messages":[{"role":"user","content":"Hello"}]}'

Sources: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 , https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nemotron-super-3-120b.html